We are looking for an AI Engineer with hands-on experience in Large Language Models (LLMs), Generative AI, and modern AI frameworks. The ideal candidate will design, develop, and deploy intelligent AI applications powered by state-of-the-art language models. You will work closely with product, engineering, and data teams to build scalable AI solutions that solve real-world business problems.

Key Responsibilities

• Design, develop, and deploy LLM-powered applications and AI agents.
• Build Retrieval-Augmented Generation (RAG) pipelines using vector databases.
• Develop prompt engineering strategies and optimize model performance.
• Integrate LLM APIs (OpenAI, Anthropic, Google Gemini, Azure OpenAI, etc.) into applications.
• Fine-tune and evaluate open-source LLMs where applicable.
• Develop AI workflows using frameworks such as LangChain, LlamaIndex, CrewAI, AutoGen, or similar.
• Build REST APIs and microservices for AI applications.
• Implement AI guardrails, content moderation, and security best practices.
• Optimize inference performance, latency, and operational costs.
• Collaborate with cross-functional teams to deliver production-ready AI solutions.
• Stay current with emerging AI technologies, research, and industry trends.

Required Skills

• -
• Strong proficiency in Python.
• - Experience with Large Language Models and Generative AI.
• - Hands-on experience with LangChain, LlamaIndex, CrewAI, AutoGen, or similar frameworks.
• - Knowledge of RAG architectures and vector databases (Pinecone, Weaviate, Chroma, FAISS, Milvus, etc.).
• - Experience with embedding models and semantic search.
• - Familiarity with OpenAI, Anthropic, Gemini, Azure OpenAI, or open-source LLMs (Llama, Mistral, Qwen, etc.).
• - Experience with FastAPI, Flask, or Django.
• - Strong understanding of REST APIs and cloud platforms (AWS, Azure, or GCP).
• - Knowledge of Docker, Kubernetes, and CI/CD pipelines.
• - Familiarity with Git and software development best practices.
• - Understanding of AI evaluation metrics, prompt optimization, and model monitoring.